© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13421
    Prev
    Next
    INDEX
    Explanations

    phrases related to baseball plays involving hits, scoring, and actions on the field

    oai_token-act-pair · gpt-3.5-turbo

    articles preceding nouns in a sports-related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shape
    -0.78
     Investigator
    -0.74
     ®
    -0.73
    onge
    -0.71
    lime
    -0.70
    SOURCE
    -0.69
    notes
    -0.67
    Enlarge
    -0.67
    ATURES
    -0.66
    encies
    -0.66
    POSITIVE LOGITS
     whopping
    1.09
     terrific
    1.03
     plethora
    1.00
    venge
    0.98
     rematch
    0.95
     lengthy
    0.93
     sizable
    0.92
     sizeable
    0.91
     timely
    0.91
     flurry
    0.91
    Activations Density 0.272%

    No Known Activations